What is the JEV Stock Decision Maker?

A Streamlit demo that turns live market data into structured investment decisions using TypeSafe Jev. It pulls real-time prices, valuation ratios and sector context with yfinance, then runs a 20-question decision model over the assembled state.

What does the 20-question model decide?

The overall action (BUY, HOLD or SELL), valuation attractiveness, balance-sheet strength, momentum and relative strength, macro sensitivity and risk, and upside probability with catalysts, using Choice, Score and Noul questions.

What market data does it cover?

Broad indices, sector ETFs and thematic ETFs with multi-horizon returns and valuation multiples, plus per-ticker fundamentals, margins, growth, debt and analyst targets for a deep dive on any stock.

What do I need to run it?

Python with streamlit, yfinance, pandas and typesafe-sdk installed, plus a TypeSafe API key set as JEV_API_KEY in .streamlit/secrets.toml. Then run streamlit run app.py from the project directory.

Is this investment advice?

No. The README labels the project demo only, not financial or investment advice, dated September 2026. The GitHub metadata also lists no license, so treat the code as reference material.

How does Jev fit into the app?

Jev acts as the decision engine: the app builds a rich state document from fundamentals and market context, and the model returns structured, auditable answers that the Streamlit UI can score, rank and display programmatically.

Can I ask my own questions?

Yes, there is a quick Q&A tab for free-form follow-up questions grounded in the same state document, so answers stay tied to the fetched market data rather than general model knowledge.

Jev directory

CommunityJev Demos & Experiments

JEV Stock Decision Maker

Streamlit demo that turns live market data into structured investment decisions with TypeSafe Jev: yfinance supplies prices and fundamentals, then a 20-question model scores buy/sell conviction, financial health and risk.

See highlights Open github.com

Stars: 1
Language: Python
Reading time: 2 min
Published by: Community
Author: 0xzee
Last verified: Oct 2026

0xzee/jev-stock-decision-maker

User repository on GitHub

View on GitHub

JEV Decision is a live demo that turns market data into structured decisions. It pulls real-time prices, valuation ratios and sector context, then runs a 20-question against TypeSafe Jev model to score buy/sell conviction, financial health and risk

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity catalog-import logicrw finance stocks streamlit

Works forJev for Scoring Jev for Classification

Used inJev for Finance & Fintech

Languages: Python
Platforms: Browser
Capabilities: Open sourceRequires API key

Highlights

Pulls live prices, multi-horizon returns and valuation multiples for broad indices, sector ETFs and thematic ETFs through yfinance.
A 20-question model scores the overall action (BUY/HOLD/SELL), valuation attractiveness, balance-sheet strength, momentum, macro risk and upside probability.
Ticker deep-dives cover fundamentals, margins, growth, debt and analyst targets; question types are Choice, Score (1-5) and Noul justifications.
Set JEV_API_KEY in .streamlit/secrets.toml and run streamlit run app.py; the README labels it demo only and not financial or investment advice.
Also offers quick free-form Q&A grounded in the same state document, so follow-ups stay inside the assembled market context.

Quickstart

bash

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
streamlit run app.py

Watch out

Copy reviewed against the repo README on 2026-10-15. GitHub metadata lists no license for the repo, and the README closes with a demo-only notice stating it is not financial or investment advice, dated September 2026.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.

Jev Demos & Experiments#gaming#agents#control

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai